requests+多进程poll+pymongo实现抓取小说

今天看着有个很吸引人的小说作品信息：一家只在深夜开门营业的书屋，欢迎您的光临。
作为东野奎吾《深夜食堂》漫画的fans，看到这个标题按捺不住我的好奇心........

所以我又抓下来了，总共52章，下面有源码，写的有点乱哦，凑合看看，关键看结果，@~@。。。。

代码写完，几秒钟就抓取下来，比下载效率高不少，小激动~~~~~~

readme>>>环境python2，我的python2还有多长寿命；其他內库依赖见代码体现

# coding:utf-8

from multiprocessing import Pool
from lxml import etree
import requests
import pymongo

def save_mongo(data):
    client = pymongo.MongoClient('60.205.211.210',27017)
    db = client.test
    collection = db.shenyeshuwu
    collection.insert(dict(data))
    print('--------%s---------存储完毕' %data['title'])

def parse_content(url):
    resp = requests.get(url).content
    html = etree.HTML(resp)
    contents = html.xpath('//*[@id="j_chapterBox"]/div[2]/div/div[2]/p/text()|//*[@id="j_chapterBox"]/div[1]/div/div[2]/p/text()')
    return contents

def parse_html(html):
    '''
    [{
    'title':title,
    'url':url,
    'content':content
    }]
    '''
    page = etree.HTML(html)
    article_url_list = page.xpath('//ul[@class="cf"]/li/a')
    for i in article_url_list:
        url = 'http:' + i.xpath('./@href')[0]
        # print(url)
        title = i.xpath('./text()')[0]
        # print(title)
        time = i.xpath('./@title')[0]
        # print(time)
        con = parse_content(url)
        # print(con)
        data = {
            'url': url,
            'title': title,
            'time': time,
            'content': con
        }
        print(data)
        save_mongo(data)



def get_page(url):
    header = {
        'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/64.0.3282.186 Safari/537.36'
    }
    resp = requests.get(url,headers=header).content
    parse_html(resp)

def main():
    url = 'https://book.qidian.com/info/1011335417#Catalog'
    # get_page(url)
    # 使用进程池　　map(func,iterable)
    pool = Pool(4)
    # pool.map(parse_content,data)
    pool.apply_async(get_page,args=(url,))
    pool.close()
    pool.join()


if __name__ == '__main__':
    main()

如往常，把截图展示下：